Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4343
    Prev
    Next
    INDEX
    Explanations

    instances where someone is being invited to an event or gathering

    oai_token-act-pair · gpt-3.5-turbo

    mentions of invitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reversal
    -0.65
     recovery
    -0.65
    atures
    -0.65
     Recovery
    -0.64
    oper
    -0.63
     Theft
    -0.63
     struggle
    -0.63
    DER
    -0.62
    strip
    -0.62
    store
    -0.61
    POSITIVE LOGITS
     invited
    3.45
     invite
    2.08
     invites
    2.06
     invitation
    1.88
     invitations
    1.87
     inviting
    1.51
     recruited
    1.49
     welcomed
    1.43
     encouraged
    1.41
     summoned
    1.40
    Activations Density 0.021%

    No Known Activations